{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WOJH2O4VDSXIXR432G3YVVYSK","short_pith_number":"pith:5WOJH2O4","schema_version":"1.0","canonical_sha256":"ed9c93e9dca8e5745e3cde8dbc56b8929e44b2cb3d5f757fa227cc3fa91aede6","source":{"kind":"arxiv","id":"2406.05797","version":2},"attestation_state":"computed","paper":{"title":"3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jinhua Zhu, Kaiyuan Gao, Lijun Wu, Qizhi Pei, Rui Yan","submitted_at":"2024-06-09T14:20:55Z","abstract_excerpt":"The integration of molecular and natural language representations has emerged as a focal point in molecular science, with recent advancements in Language Models (LMs) demonstrating significant potential for comprehensive modeling of both domains. However, existing approaches face notable limitations, particularly in their neglect of three-dimensional (3D) information, which is crucial for understanding molecular structures and functions. While some efforts have been made to incorporate 3D molecular information into LMs using external structure encoding modules, significant difficulties remain,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.05797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-06-09T14:20:55Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"title_canon_sha256":"5aa6c6c8af9a3056443d87e777a84d0159c7e4a304dfe36e134ed58cf873f85a","abstract_canon_sha256":"fd4b44a8441efd16db972e2d761eca658ee1e30fb6a8c2310e7e15d146659b89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:34.382988Z","signature_b64":"1mQ9e5VpCuf4/7ga/vOwI2xxB9rtWFs9tjRogxnVkWXSAJtajTdhGSaavB60fi7l3UjWzrLFExaZqR+8vXQjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed9c93e9dca8e5745e3cde8dbc56b8929e44b2cb3d5f757fa227cc3fa91aede6","last_reissued_at":"2026-07-05T10:33:34.379169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:34.379169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Jinhua Zhu, Kaiyuan Gao, Lijun Wu, Qizhi Pei, Rui Yan","submitted_at":"2024-06-09T14:20:55Z","abstract_excerpt":"The integration of molecular and natural language representations has emerged as a focal point in molecular science, with recent advancements in Language Models (LMs) demonstrating significant potential for comprehensive modeling of both domains. However, existing approaches face notable limitations, particularly in their neglect of three-dimensional (3D) information, which is crucial for understanding molecular structures and functions. While some efforts have been made to incorporate 3D molecular information into LMs using external structure encoding modules, significant difficulties remain,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05797","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.05797/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.05797","created_at":"2026-07-05T10:33:34.379252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05797v2","created_at":"2026-07-05T10:33:34.379252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05797","created_at":"2026-07-05T10:33:34.379252+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WOJH2O4VDSX","created_at":"2026-07-05T10:33:34.379252+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WOJH2O4VDSXIXR4","created_at":"2026-07-05T10:33:34.379252+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WOJH2O4","created_at":"2026-07-05T10:33:34.379252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02810","citing_title":"Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK","json":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK.json","graph_json":"https://pith.science/api/pith-number/5WOJH2O4VDSXIXR432G3YVVYSK/graph.json","events_json":"https://pith.science/api/pith-number/5WOJH2O4VDSXIXR432G3YVVYSK/events.json","paper":"https://pith.science/paper/5WOJH2O4"},"agent_actions":{"view_html":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK","download_json":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK.json","view_paper":"https://pith.science/paper/5WOJH2O4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05797&json=true","fetch_graph":"https://pith.science/api/pith-number/5WOJH2O4VDSXIXR432G3YVVYSK/graph.json","fetch_events":"https://pith.science/api/pith-number/5WOJH2O4VDSXIXR432G3YVVYSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK/action/storage_attestation","attest_author":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK/action/author_attestation","sign_citation":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK/action/citation_signature","submit_replication":"https://pith.science/pith/5WOJH2O4VDSXIXR432G3YVVYSK/action/replication_record"}},"created_at":"2026-07-05T10:33:34.379252+00:00","updated_at":"2026-07-05T10:33:34.379252+00:00"}